Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to sketches, both as an activity and an outcome

    oai_token-act-pair · gpt-3.5-turbo

    references to sketches and sketchy behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rogens
    -0.79
    judicial
    -0.69
    Ïī
    -0.68
    ishops
    -0.67
    pha
    -0.64
    çĦ
    -0.62
     Spears
    -0.62
    elsen
    -0.61
     iod
    -0.61
    undai
    -0.61
    POSITIVE LOGITS
     sketch
    1.02
     sketches
    0.96
    BOOK
    0.93
    book
    0.91
    pad
    0.85
    smanship
    0.84
    Artist
    0.83
    eers
    0.81
    enegger
    0.81
    y
    0.79
    Act Density 0.027%

    No Known Activations